INDEX

Explanations

references to specific texts or titles

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 webs

-1.02

 cust

-1.02

iHUD

-0.90

catentry

-0.87

byn

-0.87

Node

-0.86

 jelly

-0.85

 bees

-0.85

mys

-0.83

 spider

-0.83

POSITIVE LOGITS

 Savage

1.58

 Rush

1.53

 Kessler

1.41

 Limbaugh

1.40

Rush

1.32

 Lambert

1.23

 Logan

1.19

 Lerner

1.18

 Hopkins

1.13

 Shapiro

1.13

Activations Density 0.403%

references to specific texts or titles

No Comments

No Known Activations